How to Connect tl;dv to Cursor via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → tl;dv, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

tl;dv + Cursor

Let your AI read your tl;dv meeting recordings: find meetings from Google Meet, Zoom and Teams, read the AI notes, topics and full transcripts, and with your confirmation import a recording from a link.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

TLDV_API_KEY

Step 1 — Get credentials

1. Sign in to tl;dv and open Settings → Personal settings → API keys (https://tldv.io/app/settings/personal-settings/api-keys).
2. Generate a key and paste it into TLDV_API_KEY. The connector sends it in the x-api-key header, only to tl;dv.
3. Check the setup with tldv_list_meetings.

Only meetings of paid organizers: the key acts as its user, and tl;dv only exports meetings whose organizer (the person who sent the calendar invite) has a paid plan: Pro, Business or Enterprise. A meeting you can see in the app but that someone on the free plan organised is not exported, even when it was shared with you: it is missing from the list or answers 403.

Recordings and transcripts are personal data: they hold what colleagues, customers and other participants said, with their names and email addresses. The AI fetches only what your question needs, prefers the AI notes over the full transcript, and does not copy transcripts to other systems unless you ask for it.

How to work: tldv_list_meetings finds meetings by a search word in the name, a date range, internal or external meetings, or only those you took part in; it returns pages of up to 100 with the total, and the AI asks for the next page while there are more. tldv_get_meeting reads one meeting (date, duration, organizer, invitees, template), and tldv_get_notes reads tl;dv's AI notes: the notes in Markdown and the topics with their summaries, each tied to the second of the recording it refers to. tldv_get_transcript returns what was said, 700 lines at a time as start second, speaker and text; for longer meetings tldv_get_transcript_more adds lines 701 to 1400. tl;dv sends no further pages, so for very long meetings the AI relies on the notes. tl;dv only returns finished transcripts.

Import asks first: tldv_import_meeting brings in a recording from a public link to an mp3, mp4, wav, m4a, mkv, mov, avi, wma or flac file, so tl;dv transcribes it and writes notes. It creates a new meeting in your account, so the AI confirms the link and the name with you and waits for your yes; dry_run checks the request without importing. Nothing is switched off at install, and no tool changes or deletes existing meetings.

Common errors: 401 AuthorizationRequiredError or UnauthorizedError: the key is missing, wrong or revoked; generate a new one. 403: the meeting's organizer has no paid plan, or you may not export that meeting. 404 NotFoundError: wrong meeting id, or the transcript or notes are not ready yet. 400: a parameter has the wrong format and the message names it (meeting ids are 24 hexadecimal characters). 429: tl;dv is limiting the requests; wait a minute.

The connector does not download the recording file itself, upload files in parts or set up webhooks (MeetingReady and TranscriptReady are configured in tl;dv's settings).

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Cursor

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Cursor reads MCP servers from ~/.cursor/mcp.json. Add this entry:

{
  "mcpServers": {
    "anythingmcp": {
      "url": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart Cursor.
3. Open Cursor → Settings → MCP and check that anythingmcp is listed and connected.
4. Start chatting: the agent can now call the tl;dv tools.

Available tools

Example prompts

• "What were the key points and next steps of my last customer call in tl;dv?"
• "List my external meetings from last week with their duration and who organised each one."
• "Find the tl;dv meeting about the onboarding redesign and tell me what was decided about the timeline."
• "Read the transcript of Tuesday's interview with Marco Rossi and pull out everything he said about his last job."
• "Import the recording at https://example.com/recordings/kickoff.mp4 into tl;dv as Kickoff Nordwind. Check the link and the name with me first."

FAQ

Does Cursor support custom MCP servers on the free tier? Yes, MCP is available on Hobby, Pro and Business plans.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT